INDEX

Explanations

phrases or words related to positional relationships or comparisons

oai_token-act-pair · gpt-3.5-turbo

phrases related to significant moments or transitions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ń·

-0.80

 DRAG

-0.75

ļéĨĴ

-0.73

QC

-0.72

 Scrib

-0.69

 appropri

-0.69

HCR

-0.68

 Kimmel

-0.67

Zup

-0.67

ħĭ

-0.66

POSITIVE LOGITS

dozen

1.26

assed

1.22

hour

1.21

century

1.18

sized

1.15

heartedly

1.14

hearted

1.12

season

1.06

hours

1.02

empty

1.01

Activations Density 0.033%

phrases or words related to positional relationships or comparisons

phrases related to significant moments or transitions

No Comments

No Known Activations